A master thesis from Aalborg University
Multi-dimensional Classification - Data Mining using Data Cubes
Author(s)
Term
4. term
Education
Publication year
2003
Submitted on
2012-02-14
Abstract
This thesis deals with the use of data mining on data warehouse structured data, also known as multi-dimensional data. The theory regarding data warehouses is investigated with the purpose of understanding the structure of data in these. Then a data set, dealing with the sales of products, and the payments of the customers, is analysed. There are to goals for this analysis, one is to create a multi-dimensional design, the other, and more important, is to get experience in creating such designs, to understand the structure of the designs better. Then it is tried to analyse the multi-dimensional data using a traditional data mining tool, Clementine. The aim of this analysis is to discover weaknesses in traditional data mining tools when dealing with multi-dimensional data. We then propose a way to analyse multi-dimensional data in general, and we propose changes to decision tree induction algorithms such that they utilise the multi-dimensional structure better. Finally, we evaluate the proposed way to analyse multi-dimensional data using a prototype of a graphical interface, and we analyse some of the proposed changed to decision tree induction using the data set we have been working with.
Documents
Colophon: This page is part of the AAU Student Projects portal, which is run by Aalborg University. Here, you can find and download publicly available bachelor's theses and master's projects from across the university dating from 2008 onwards. Student projects from before 2008 are available in printed form at Aalborg University Library.
If you have any questions about AAU Student Projects or the research registration, dissemination and analysis at Aalborg University, please feel free to contact the VBN team. You can also find more information in the AAU Student Projects FAQs.